Interpretability

Quantifying the Effect of Test Set Contamination on Generative Evaluations
Context Matters: Analyzing the Generalizability of Linear Probing and Steering Across Diverse Scenarios
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
Precise In-Parameter Concept Erasure in Large Language Models
Do Sparse Autoencoders Generalize? A Case Study of Answerability
Scaling Sparse Feature Circuit Finding for In-Context Learning
Towards Interpreting Visual Information Processing in Vision-Language Models
Interpreting Learned Feedback Patterns in Large Language Models
Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions